update comando api

scraper/scrapers/comando/comando_api.js

@@ -29,7 +29,7 @@ function torrent(torrentId, config = {}, retries = 2) {
       .then((torrent) => torrent.map(el => ({ torrentId: slug, ...el })))
       .catch((err) => {
         console.warn(`Failed Comando ${slug} request: `, err);
-        return torrent(slug, config, retries - 1)
+        return torrent(torrentId, config, retries - 1)
       });
 }
 
@@ -116,14 +116,14 @@ function parseTorrentPage(body) {
     const torrents = magnets.map(magnetLink => {
       const decodedMagnet = decode(magnetLink);
       const originalNameElem = details.find('strong, b')
-          .filter((i, elem) => $(elem).text().match(/Baixar|Orig(?:\.|inal)/));
+          .filter((i, elem) => $(elem).text().match(/Baixar|Orig(?:\.|inal)|^Título:/));
       const languagesElem = details.find('strong, b')
           .filter((i, elem) => $(elem).text().match(/^\s*([IÍ]dioma|[AÁ]udio)/));
-      const originalName = originalNameElem.next().text().trim() || originalNameElem[0].nextSibling.nodeValue;
+      const originalName = parseOriginalName(originalNameElem);
       const title = decodedMagnet.name && escapeHTML(decodedMagnet.name.replace(/\+/g, ' '));
       return {
-        title: title ? sanitizePtName(title) : originalName.replace(/: ?/, ''),
+        title: title ? sanitizePtName(title) : originalName,
-        originalName: sanitizePtOriginalName(originalName.replace(/: ?/, '')),
+        originalName: sanitizePtOriginalName(originalName),
         year: details.find('a[href*="comando.to/category/"]').text(),
         infoHash: decodedMagnet.infoHash,
         magnetLink: magnetLink,
@@ -137,6 +137,14 @@ function parseTorrentPage(body) {
   });
 }
 
+function parseOriginalName(originalNameElem) {
+  if (!originalNameElem[0]) {
+    return '';
+  }
+  const originalName = originalNameElem.next().text().trim() || originalNameElem[0].nextSibling.nodeValue;
+  return originalName.replace(/: ?/, '');
+}
+
 function parseCategory(categorys) {
   const $ = cheerio.load(categorys)
   if ($('a:contains(\'animes\')').text()) {

scraper/scrapers/comando/comando_scraper.js

@@ -72,7 +72,7 @@ async function processTorrentRecord(foundTorrent) {
   if (!Number.isInteger(foundTorrent.seeders)) {
     await updateCurrentSeeders(foundTorrent);
   }
-  if (!foundTorrent.imdbId) {
+  if (!foundTorrent.imdbId && foundTorrent.originalName) {
     const info = { title: foundTorrent.originalName, year: foundTorrent.year };
     foundTorrent.imdbId = await getImdbId(info, TYPE_MAPPING[foundTorrent.category]).catch(() => undefined);
   }

scraper/scrapers/comoeubaixo/comoeubaixo_api.js

@@ -21,13 +21,13 @@ function torrent(torrentId, config = {}, retries = 2) {
   if (!torrentId || retries === 0) {
     return Promise.reject(new Error(`Failed ${torrentId} query`));
   }
-  const slug = torrentId.split("/")[3];
+  const slug = encodeURIComponent(torrentId.split("/")[3]);
   return singleRequest(`${baseUrl}/${slug}/`, config)
       .then((body) => parseTorrentPage(body))
       .then((torrent) => torrent.map(el => ({ torrentId: slug, ...el })))
       .catch((err) => {
-        console.warn(`Failed ComoEuBaixo ${slug} request: `, err);
+        console.warn(`Failed ComoEuBaixo ${torrentId} request: `, err);
-        return torrent(slug, config, retries - 1)
+        return torrent(torrentId, config, retries - 1)
       });
 }
 
@@ -67,7 +67,7 @@ function singleRequest(requestUrl, config = {}) {
   return needle('get', requestUrl, options)
       .then((response) => {
         const body = response.body;
-        if (!body) {
+        if (!body || (Buffer.isBuffer(body) && !body.size)) {
           throw new Error(`No body: ${requestUrl}`);
         } else if (body.includes('502: Bad gateway') ||
             body.includes('403 Forbidden')) {
@@ -118,7 +118,7 @@ function parseTorrentPage(body) {
       const year = details.find('strong:contains(\'Data de Lançamento: \')').next().text().trim();
       const fallBackTitle = `${originalTitle.trim()} ${year.trim()} ${sanitizedTitle.trim()}`;
       return {
-        title: sanitizedTitle.length > 4 ? sanitizedTitle : fallBackTitle,
+        title: sanitizedTitle.length > 5 ? sanitizedTitle : fallBackTitle,
         infoHash: decode(magnetLink).infoHash,
         magnetLink: magnetLink,
         category: category,

scraper/scrapers/lapumia/lapumia_api.js

@@ -27,7 +27,7 @@ function torrent(torrentId, config = {}, retries = 2) {
       .then((torrent) => torrent.map(el => ({ torrentId: slug, ...el })))
       .catch((err) => {
         console.warn(`Failed Lapumia ${slug} request: `, err);
-        return torrent(slug, config, retries - 1)
+        return torrent(torrentId, config, retries - 1)
       });
 }
 

scraper/scrapers/ondebaixa/ondebaixa_api.js

@@ -27,7 +27,7 @@ function torrent(torrentId, config = {}, retries = 2) {
       .then((torrent) => torrent.map(el => ({ torrentId: slug, ...el })))
       .catch((err) => {
         console.warn(`Failed OndeBaixo ${slug} request: `, err);
-        return torrent(slug, config, retries - 1)
+        return torrent(torrentId, config, retries - 1)
       });
 }
 

scraper/scrapers/scraperHelper.js

@@ -5,8 +5,9 @@ function isPtDubbed(name) {
 function sanitizePtName(name) {
   return name
       .replace(/(.*)\b(\d{3,4}P)\b(?!.*\d{3,4}[Pp])(.*)/, '$1$3 $2') // add resolution to the end if missing
-      .replace(/^[[{]?(?:ACESSE.*|WWW\.)?[A-Z]+\.(COM|ORG|TO|TV)\b\s?[-\]}]+[\s.]*/i, '') // replace watermarks
+      .replace(/^[[{]?(?:ACESSE.*|WWW\.)?[A-Z]+\.(COM|NET|ORG|TO|TV|ME)\b\s*[-\]}]+[\s.]*/i, '') // replace watermarks
       .replace(/^(\d*(?:\.\d{1,2})?(?:[4A-Z-]{3,}|P)[-.]+)+/, '') // replace metadata prefixes
+      .replace(/^(COM|NET|ORG|TO|TV|ME)\b\s*-+[\s.]*/, '') // replace dangling site endings
       .trim();
 }